```

feat(AI): 统一多模态模型架构，整合文本和视觉推理路径 - 将文本生成和VL(图→文)功能合并到单一的Qwen3.5-4B多模态MNN模型 - 移除独立的Qwen3-VL-4B模型依赖，MLX VL改为使用.llm的多模态模型 - 更新ModelKind枚举，新增userFacing集合用于面向用户展示 - MNN后端现在同时支持文本和视觉任务，模拟器回退到MLX refactor(models): 模型管理和界面调整以适应新的多模态架构 - 更新模型管理界面，只显示统一的Qwen3.5-4B(MNN)模型给用户 - 修改就绪状态检查逻辑，使用ModelKind.userFacing替代allCases - 更新模型文件清单，从Qwen3.5-2B升级到Qwen3.5-4B-4bit - 调整模型管理页面UI，突出MNN+SME2端侧加速功能 feat(camera): 添加拍照识别引擎切换功能 - 实现双路径拍照识别：Apple Vision OCR + 文本模型和 Qwen3-VL直接识别 - 添加预处理逻辑，优化Qwen3-VL对窄长区域图片的识别效果 - 在模型管理页面添加拍照识别引擎选择组件 - 提供用户界面选项，在两种识别方式间切换 style(ui): 优化输入框样式和颜色主题一致性 - 为指标快速表单添加浅色主题偏好 - 统一所有文本输入框的颜色样式(theme) - 创建EntryInputField组件，替换原有的单行输入+按钮模式 - 实现聊天框风格的条目输入，支持多行自适应和圆形发送按钮 fix(build): 修正Xcode项目配置中的重复框架搜索路径 - 清理project.pbxproj中重复的FRAMEWORK_SEARCH_PATHS配置 - 重新排列Swift桥接头文件配置确保正确引用 - 修复因路径配置重复导致的编译警告问题 test: 增加区域图片预处理和模型清单测试覆盖 - 添加RegionImageCropper.prepareForQwenVL的单元测试 - 验证宽而矮图片的放大和填充逻辑 - 更新ModelManifestTests中的字节数预期值以匹配新模型 - 修正OCRService中VNRecognizedTextObservation类型的处理 ```
2026-06-08 23:25:31 +08:00
parent b919404412
commit 836f3d4234
20 changed files with 393 additions and 65 deletions
--- a/康康/Features/Indicator/IndicatorQuickSheet.swift
+++ b/康康/Features/Indicator/IndicatorQuickSheet.swift
@@ -143,6 +143,7 @@ struct IndicatorQuickSheet: View {
                .clipShape(RoundedRectangle(cornerRadius: Tj.Radius.xl, style: .continuous))
                .ignoresSafeArea(edges: .bottom)
        )
+        .preferredColorScheme(.light)
        .presentationDetents([.large])
        .presentationDragIndicator(.hidden)
        .presentationBackground(Tj.Palette.sand)
@@ -423,6 +424,8 @@ struct IndicatorQuickSheet: View {
            TextField(placeholder, text: value)
                .keyboardType(.decimalPad)
                .font(.tjScaled( 20, weight: .semibold, design: .monospaced))
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                .multilineTextAlignment(.center)
                .padding(.vertical, 10)
                .frame(width: 90)
@@ -468,6 +471,8 @@ struct IndicatorQuickSheet: View {
            sectionLabel(String(appLoc: "指标名"))
            TextField("例如:血红蛋白", text: $name)
                .textInputAutocapitalization(.never)
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                .padding(.horizontal, 14)
                .padding(.vertical, 12)
                .background(fieldBg)
@@ -489,6 +494,8 @@ struct IndicatorQuickSheet: View {
                TextField(monitorFieldPlaceholder, text: $value)
                    .keyboardType(.decimalPad)
                    .font(.tjScaled( 18, weight: .semibold, design: .monospaced))
+                    .foregroundStyle(Tj.Palette.text)
+                    .tint(Tj.Palette.ink)
                    .padding(.horizontal, 14)
                    .padding(.vertical, 12)
                    .background(fieldBg)
@@ -499,6 +506,8 @@ struct IndicatorQuickSheet: View {
                TextField("mmol/L", text: $unit)
                    .textInputAutocapitalization(.never)
                    .autocorrectionDisabled()
+                    .foregroundStyle(Tj.Palette.text)
+                    .tint(Tj.Palette.ink)
                    .padding(.horizontal, 14)
                    .padding(.vertical, 12)
                    .background(fieldBg)
@@ -522,6 +531,8 @@ struct IndicatorQuickSheet: View {
            TextField("例如:< 3.40 或 3.9 - 6.1", text: $range)
                .textInputAutocapitalization(.never)
                .autocorrectionDisabled()
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                .padding(.horizontal, 14)
                .padding(.vertical, 12)
                .background(fieldBg)
@@ -581,6 +592,8 @@ struct IndicatorQuickSheet: View {
            sectionLabel(String(appLoc: "备注(可选)"))
            TextField("例如:空腹采血", text: $note, axis: .vertical)
                .lineLimit(1...3)
+                .foregroundStyle(Tj.Palette.text)
+                .tint(Tj.Palette.ink)
                .padding(.horizontal, 14)
                .padding(.vertical, 12)
                .background(fieldBg)
--- a/康康/Features/Me/MeView.swift
+++ b/康康/Features/Me/MeView.swift
@@ -152,10 +152,10 @@ struct MeView: View {

    private var modelDetail: String {
        let states = downloadService.states
-        if ModelKind.allCases.allSatisfy({ states[$0]?.phase == .ready }) { return String(appLoc: "已就绪") }
+        if ModelKind.userFacing.allSatisfy({ states[$0]?.phase == .ready }) { return String(appLoc: "已就绪") }
        if downloadService.isAnyDownloading { return String(appLoc: "下载中…") }
-        let readyCount = ModelKind.allCases.filter { states[$0]?.phase == .ready }.count
-        return readyCount == 0 ? String(appLoc: "未下载") : String(appLoc: "\(readyCount)/\(ModelKind.allCases.count) 就绪")
+        let readyCount = ModelKind.userFacing.filter { states[$0]?.phase == .ready }.count
+        return readyCount == 0 ? String(appLoc: "未下载") : String(appLoc: "\(readyCount)/\(ModelKind.userFacing.count) 就绪")
    }

    private var inferenceEngineCard: some View {
--- a/康康/Features/Me/ModelManagementView.swift
+++ b/康康/Features/Me/ModelManagementView.swift
@@ -10,25 +10,29 @@ struct ModelManagementView: View {
    @State private var showCellularConfirm = false
    @State private var showImporter = false
    @State private var importError: String?
+    @AppStorage(QuickRegionRecognitionEngine.storageKey)
+    private var quickRegionEngineRaw = QuickRegionRecognitionEngine.defaultValue.rawValue

    private let monitor = NWPathMonitor()
    private let monitorQueue = DispatchQueue(label: "kk.netmonitor")

    private var allReady: Bool {
-        ModelKind.allCases.allSatisfy { service.states[$0]?.phase == .ready }
+        ModelKind.userFacing.allSatisfy { service.states[$0]?.phase == .ready }
    }

    var body: some View {
        ScrollView {
            VStack(spacing: 14) {
-                ForEach(ModelKind.allCases, id: \.self) { kind in
+                ForEach(ModelKind.userFacing, id: \.self) { kind in
                    modelCard(kind)
                }

+                recognitionEngineCard
+
                actionButtons
                    .padding(.top, 4)

-                if service.states[.llm]?.phase == .ready {
+                if service.states[.mnnLLM]?.phase == .ready {
                    NavigationLink {
                        ModelSelfTestView()
                    } label: {
@@ -76,6 +80,46 @@ struct ModelManagementView: View {
        }
    }

+    // MARK: - 拍照识别引擎
+
+    private var selectedRecognitionEngine: QuickRegionRecognitionEngine {
+        QuickRegionRecognitionEngine(storedValue: quickRegionEngineRaw)
+    }
+
+    private var recognitionEngineCard: some View {
+        VStack(alignment: .leading, spacing: 12) {
+            HStack(alignment: .top, spacing: 10) {
+                ZStack {
+                    Circle().fill(Tj.Palette.sand2)
+                    Image(systemName: "camera.metering.center.weighted")
+                        .font(.tjScaled( 18))
+                        .foregroundStyle(Tj.Palette.text2)
+                }
+                .frame(width: 38, height: 38)
+
+                VStack(alignment: .leading, spacing: 3) {
+                    Text("异常项拍照识别")
+                        .font(.tjScaled( 15, weight: .semibold))
+                        .foregroundStyle(Tj.Palette.text)
+                    Text(selectedRecognitionEngine.detail)
+                        .font(.tjScaled( 12))
+                        .foregroundStyle(Tj.Palette.text3)
+                }
+                Spacer()
+            }
+
+            Picker("异常项拍照识别", selection: $quickRegionEngineRaw) {
+                ForEach(QuickRegionRecognitionEngine.allCases) { engine in
+                    Text(engine.title).tag(engine.rawValue)
+                }
+            }
+            .pickerStyle(.segmented)
+        }
+        .padding(14)
+        .frame(maxWidth: .infinity, alignment: .leading)
+        .tjCard()
+    }
+
    // MARK: - 模型卡片

    private func modelCard(_ kind: ModelKind) -> some View {
@@ -146,7 +190,7 @@ struct ModelManagementView: View {
    private var actionButtons: some View {
        if service.isAnyDownloading {
            Button {
-                for kind in ModelKind.allCases { service.cancel(kind) }
+                for kind in ModelKind.userFacing { service.cancel(kind) }
            } label: {
                Text("暂停下载").frame(maxWidth: .infinity)
            }
@@ -154,7 +198,7 @@ struct ModelManagementView: View {
        } else if allReady {
            HStack(spacing: 6) {
                Image(systemName: "checkmark.seal.fill")
-                Text("两个模型都已就绪")
+                Text("Qwen3.5-4B 已就绪")
            }
            .font(.tjScaled( 13, weight: .semibold))
            .foregroundStyle(Tj.Palette.leaf)
@@ -198,8 +242,8 @@ struct ModelManagementView: View {
            defer { if scoped { folder.stopAccessingSecurityScopedResource() } }

            let name = folder.lastPathComponent
-            guard let kind = ModelKind.allCases.first(where: { $0.rawValue == name }) else {
-                let names = ModelKind.allCases.map(\.rawValue).joined(separator: " 或 ")
+            guard let kind = ModelKind.userFacing.first(where: { $0.rawValue == name }) else {
+                let names = ModelKind.userFacing.map(\.rawValue).joined(separator: " 或 ")
                importError = String(appLoc: "请选择名为 \(names) 的文件夹")
                return
            }
@@ -213,14 +257,14 @@ struct ModelManagementView: View {
    // MARK: - 辅助

    private var totalAllBytes: Int {
-        ModelKind.allCases.reduce(0) { $0 + ModelManifest.totalBytes(for: $1) }
+        ModelKind.userFacing.reduce(0) { $0 + ModelManifest.totalBytes(for: $1) }
    }

    private func subtitle(_ kind: ModelKind) -> String {
        switch kind {
        case .llm:    return String(appLoc: "文本解读 · 趋势 / 问答(MLX 兜底)")
        case .vl:     return String(appLoc: "拍照识别报告 → 结构化指标")
-        case .mnnLLM: return String(appLoc: "文本解读 · MNN + SME2 端侧加速")
+        case .mnnLLM: return String(appLoc: "文本解读 + 拍照识别 · MNN + SME2 端侧加速")
        }
    }

--- a/康康/Features/Profile/ProfileEditView.swift
+++ b/康康/Features/Profile/ProfileEditView.swift
@@ -370,17 +370,14 @@ private struct ChronicSection: View {
                }
            }

-            HStack {
-                TextField("自定义慢病", text: $newCustomCondition)
-                Button("加") {
-                    let trimmed = newCustomCondition.trimmingCharacters(in: .whitespaces)
-                    guard !trimmed.isEmpty,
-                          !profile.chronicConditions.contains(trimmed) else { return }
-                    profile.chronicConditions.append(trimmed)
-                    newCustomCondition = ""
-                }
-                .disabled(newCustomCondition.trimmingCharacters(in: .whitespaces).isEmpty)
+            EntryInputField(placeholder: String(appLoc: "自定义慢病"), text: $newCustomCondition) {
+                let trimmed = newCustomCondition.trimmingCharacters(in: .whitespaces)
+                guard !trimmed.isEmpty,
+                      !profile.chronicConditions.contains(trimmed) else { return }
+                profile.chronicConditions.append(trimmed)
+                newCustomCondition = ""
            }
+            .listRowBackground(Color.clear)
        } header: {
            Text("慢病(影响参考范围与 AI 解读)")
        }
@@ -408,6 +405,48 @@ private struct ChronicSection: View {
    }
 }

+// MARK: - 聊天框风格的条目输入(圆角容器 + 多行增长 + 圆形发送按钮)
+
+/// 替代原先单行 `TextField + “加”` 的搜索框观感:文字随内容换行增长(1~4 行),
+/// 右侧圆形发送按钮(内容为空时禁用变灰)。过敏 / 家族史 / 用药 / 自定义慢病共用。
+private struct EntryInputField: View {
+    let placeholder: String
+    @Binding var text: String
+    var onSubmit: () -> Void
+
+    private var canSubmit: Bool {
+        !text.trimmingCharacters(in: .whitespaces).isEmpty
+    }
+
+    var body: some View {
+        HStack(alignment: .bottom, spacing: 8) {
+            TextField(placeholder, text: $text, axis: .vertical)
+                .lineLimit(1...4)
+                .padding(.horizontal, 14)
+                .padding(.vertical, 10)
+                .background(
+                    RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                        .fill(Tj.Palette.paper)
+                )
+                .overlay(
+                    RoundedRectangle(cornerRadius: Tj.Radius.md, style: .continuous)
+                        .strokeBorder(Tj.Palette.line, lineWidth: 1)
+                )
+
+            Button {
+                if canSubmit { onSubmit() }
+            } label: {
+                Image(systemName: "arrow.up.circle.fill")
+                    .font(.tjScaled(28))
+                    .foregroundStyle(canSubmit ? Tj.Palette.ink : Tj.Palette.text3)
+            }
+            .buttonStyle(.plain)
+            .disabled(!canSubmit)
+        }
+        .padding(.vertical, 2)
+    }
+}
+
 // MARK: - 过敏 / 家族史 / 用药(每节自带 @State,敲字只重算本节)

 private struct StringListSection: View {
@@ -431,16 +470,13 @@ private struct StringListSection: View {
                    .buttonStyle(.borderless)
                }
            }
-            HStack {
-                TextField(placeholder, text: $newInput)
-                Button("加") {
-                    let trimmed = newInput.trimmingCharacters(in: .whitespaces)
-                    guard !trimmed.isEmpty, !items.contains(trimmed) else { return }
-                    items.append(trimmed)
-                    newInput = ""
-                }
-                .disabled(newInput.trimmingCharacters(in: .whitespaces).isEmpty)
+            EntryInputField(placeholder: placeholder, text: $newInput) {
+                let trimmed = newInput.trimmingCharacters(in: .whitespaces)
+                guard !trimmed.isEmpty, !items.contains(trimmed) else { return }
+                items.append(trimmed)
+                newInput = ""
            }
+            .listRowBackground(Color.clear)
        }
    }
 }
--- a/康康/Features/Quick/QuickRegionCaptureFlow.swift
+++ b/康康/Features/Quick/QuickRegionCaptureFlow.swift
@@ -15,6 +15,8 @@ struct QuickRegionCaptureFlow: View {
    @Environment(\.modelContext) private var ctx
    let onClose: () -> Void

+    @AppStorage(QuickRegionRecognitionEngine.storageKey)
+    private var recognitionEngineRaw = QuickRegionRecognitionEngine.defaultValue.rawValue
    @State private var phase: Phase = .idle

    enum Phase {
@@ -98,8 +100,20 @@ struct QuickRegionCaptureFlow: View {
    // MARK: - 识别(框内子图 → OCR → LLM)

    /// 对已裁好的框内子图跑识别。失败/超时返回提示文案,绝不抛出(由 RegionAdjustView 展示)。
-    /// 链路:Vision 端侧 OCR 取文本 → Qwen3-1.7B 结构化抽指标(对齐 indicator-capture-ocr-llm)。
+    /// 链路由「我的 → 模型管理 → 拍照识别引擎」决定:
+    /// - Apple Vision:Vision 端侧 OCR → Qwen3-1.7B 结构化抽指标
+    /// - Qwen3-VL:局部图片 → Qwen3-VL 直接结构化抽指标
    private func recognizeRegion(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
+        let engine = QuickRegionRecognitionEngine(storedValue: recognitionEngineRaw)
+        switch engine {
+        case .appleVision:
+            return await recognizeWithAppleVision(image)
+        case .qwenVL:
+            return await recognizeWithQwenVL(image)
+        }
+    }
+
+    private func recognizeWithAppleVision(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
        do {
            let text = try await OCRService.recognizeText(in: image)
            if Task.isCancelled { return ([], nil) }   // 超时:文案由调用方给
@@ -125,6 +139,30 @@ struct QuickRegionCaptureFlow: View {
        }
    }

+    private func recognizeWithQwenVL(_ image: UIImage) async -> (items: [QuickRegionItem], warning: String?) {
+        let prepared = RegionImageCropper.prepareForQwenVL(image)
+        guard let data = prepared.jpegData(compressionQuality: 0.95) else {
+            return ([], String(appLoc: "图片编码失败,手动补充"))
+        }
+        #if DEBUG
+        print("🖼️ [Qwen3-VL region] prepared image=\(Int(prepared.size.width))x\(Int(prepared.size.height)), bytes=\(data.count)")
+        #endif
+        do {
+            let parsed = try await CaptureService.shared.recognizeRegion(imageData: data)
+            if Task.isCancelled { return ([], nil) }
+            let items = Self.buildItems(from: parsed)
+            return (items, items.isEmpty ? String(appLoc: "没读出指标,挪一下框再试") : nil)
+        } catch CaptureError.modelNotReady {
+            return ([], String(appLoc: "模型未就绪,请在模型管理下载或切回 Apple Vision"))
+        } catch let CaptureError.parseFailed(msg) {
+            return ([], String(appLoc: "解析失败:\(msg)"))
+        } catch let CaptureError.inferenceFailed(msg) {
+            return ([], Task.isCancelled ? nil : String(appLoc: "识别失败:\(msg)"))
+        } catch {
+            return ([], Task.isCancelled ? nil : String(appLoc: "未知错误:\(error.localizedDescription)"))
+        }
+    }
+
    /// LLM 结果 → 可编辑行,异常项(high/low)置顶、默认勾选。
    private static func buildItems(from parsed: [ParsedReport.ParsedIndicator]) -> [QuickRegionItem] {
        let mapped = parsed.map {
--- a/康康/Features/Quick/QuickRegionRecognitionEngine.swift
+++ b/康康/Features/Quick/QuickRegionRecognitionEngine.swift
@@ -0,0 +1,31 @@
+import Foundation
+
+enum QuickRegionRecognitionEngine: String, CaseIterable, Identifiable, Sendable {
+    case appleVision
+    case qwenVL
+
+    static let storageKey = "quickRegionRecognitionEngine"
+    static let defaultValue: QuickRegionRecognitionEngine = .appleVision
+
+    var id: String { rawValue }
+
+    init(storedValue: String) {
+        self = QuickRegionRecognitionEngine(rawValue: storedValue) ?? Self.defaultValue
+    }
+
+    var title: String {
+        switch self {
+        case .appleVision: return String(appLoc: "Apple Vision")
+        case .qwenVL:      return String(appLoc: "大模型直读")
+        }
+    }
+
+    var detail: String {
+        switch self {
+        case .appleVision:
+            return String(appLoc: "系统 OCR + 文本模型解析")
+        case .qwenVL:
+            return String(appLoc: "Qwen3.5-4B 多模态直接看图(MNN/MLX)")
+        }
+    }
+}
--- a/康康/Features/Quick/RegionCameraView.swift
+++ b/康康/Features/Quick/RegionCameraView.swift
@@ -352,6 +352,49 @@ enum RegionImageCropper {
        guard rect.width >= 1, rect.height >= 1, let cropped = cg.cropping(to: rect) else { return up }
        return UIImage(cgImage: cropped, scale: up.scale, orientation: .up)
    }
+
+    /// Qwen3-VL 局部图预处理:宽而矮的小框直接喂 VL 时,processor 再缩放容易把小字压没。
+    /// 这里只用于 Qwen3-VL 分支,Apple Vision OCR 保持吃原始裁剪图。
+    static func prepareForQwenVL(_ image: UIImage,
+                                 minimumShortEdge: CGFloat = 448,
+                                 maximumLongEdge: CGFloat = 2400,
+                                 padding: CGFloat = 64) -> UIImage {
+        let up = image.normalizedUp()
+        guard let cg = up.cgImage else { return up }
+
+        let sourceSize = CGSize(width: cg.width, height: cg.height)
+        guard sourceSize.width > 0, sourceSize.height > 0 else { return up }
+
+        let short = min(sourceSize.width, sourceSize.height)
+        let long = max(sourceSize.width, sourceSize.height)
+        var scale = max(1, minimumShortEdge / short)
+        if long * scale > maximumLongEdge {
+            scale = maximumLongEdge / long
+        }
+
+        let contentSize = CGSize(
+            width: max(1, (sourceSize.width * scale).rounded()),
+            height: max(1, (sourceSize.height * scale).rounded())
+        )
+        let canvasSize = CGSize(
+            width: contentSize.width + padding * 2,
+            height: contentSize.height + padding * 2
+        )
+
+        let format = UIGraphicsImageRendererFormat.default()
+        format.scale = 1
+        format.opaque = true
+        let renderer = UIGraphicsImageRenderer(size: canvasSize, format: format)
+        return renderer.image { ctx in
+            UIColor.white.setFill()
+            ctx.fill(CGRect(origin: .zero, size: canvasSize))
+
+            UIImage(cgImage: cg, scale: 1, orientation: .up).draw(
+                in: CGRect(x: padding, y: padding,
+                           width: contentSize.width, height: contentSize.height)
+            )
+        }
+    }
 }

 extension UIImage {